基于蚁群算法的多QoS约束海量数据网格任务调度

针对海量数据计算网格任务调度问题,提出一种多Qos约束网格任务调度蚁群改进算法,优先考虑与数据存储网格结点间数据传输效率高、完成任务概率高的网格计算资源,通过调整蚁群算法中信息素挥发因子和传输导向因子的更新方法来提高算法的收敛速度和全局最优解搜索能力,从而达到调度目标最优.仿真实验结果表明,该算法与QoS-Min-min和QoS-Sufferage等同类算法相比,具有较好的综合性能,特别是在计算数据文件较大时,该算法在收敛速度和全局最优解搜索能力方面有明显的提高.

Modified ant colony algorithm based grid task scheduling on multi-QoS constraint mass data

Aimed at problems existing in mass data grid scheduling,this paper proposes an algorithm based on modified ant colony algorithm for grid task scheduling of multi-QoS constraints.Through improving the efficiency of data transferring between nodes of computing resources and data storage,it accomplishes the scheduling task with high efficiency and short time.The algorithm is based on transferring orientation factor to modify the searching behavior of ants,and modifies the value of pheromone according to the object function,which accelerates the convergence rate and improves the ability of searching an optimum solution.Simulation shows that it performs better than the QoS-Min-min and QoS-Sufferage in the integrated performances,especially for large computing data file.